Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2770 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.3673. Min Range: -3.3673

Max Act: 3.1694. Min Act: -0.0000

Data Index: 1577511 (Python Code)

Max Activating Token Index: 974

Text #1

Max Range: 3.3673. Min Range: -3.3673

Max Act: 3.1953. Min Act: -0.0000

Data Index: 1602527 (Python Code)

Max Activating Token Index: 670

Text #2

Max Range: 3.3673. Min Range: -3.3673

Max Act: 3.2107. Min Act: -0.0000

Data Index: 1366661 (Python Code)

Max Activating Token Index: 890

Text #3

Max Range: 3.3673. Min Range: -3.3673

Max Act: 3.1535. Min Act: -0.0000

Data Index: 1651881 (Python Code)

Max Activating Token Index: 50

Text #4

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.9350. Min Act: -0.0000

Data Index: 1432724 (Python Code)

Max Activating Token Index: 437

Text #5

Max Range: 3.3673. Min Range: -3.3673

Max Act: 3.3673. Min Act: -0.0000

Data Index: 1431587 (Python Code)

Max Activating Token Index: 903

Text #6

Max Range: 3.3673. Min Range: -3.3673

Max Act: 3.2100. Min Act: -0.0000

Data Index: 1438639 (Python Code)

Max Activating Token Index: 700

Text #7

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.6828. Min Act: -0.0000

Data Index: 1373048 (Python Code)

Max Activating Token Index: 965

Text #8

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.8145. Min Act: -0.0000

Data Index: 1499528 (Python Code)

Max Activating Token Index: 450

Text #9

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.7846. Min Act: -0.0000

Data Index: 1485969 (Python Code)

Max Activating Token Index: 343

Text #10

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.9053. Min Act: -0.0000

Data Index: 1587435 (Python Code)

Max Activating Token Index: 547

Text #11

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.4380. Min Act: -0.0000

Data Index: 1414528 (Python Code)

Max Activating Token Index: 778

Text #12

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.5520. Min Act: -0.0000

Data Index: 1374634 (Python Code)

Max Activating Token Index: 579

Text #13

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.6614. Min Act: -0.0000

Data Index: 1478199 (Python Code)

Max Activating Token Index: 364

Text #14

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.5152. Min Act: -0.0000

Data Index: 1476966 (Python Code)

Max Activating Token Index: 954

Text #15

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.8996. Min Act: -0.0000

Data Index: 1451669 (Python Code)

Max Activating Token Index: 828

Text #16

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.4365. Min Act: -0.0000

Data Index: 1395727 (Python Code)

Max Activating Token Index: 309

Text #17

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.3832. Min Act: -0.0000

Data Index: 1442751 (Python Code)

Max Activating Token Index: 130

Text #18

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.2657. Min Act: -0.0000

Data Index: 1546149 (Python Code)

Max Activating Token Index: 555

Text #19

Max Range: 3.3673. Min Range: -3.3673

Max Act: 2.2390. Min Act: -0.0000

Data Index: 1474835 (Python Code)

Max Activating Token Index: 224